Module 5 Lab

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(completejourney)

## Welcome to the completejourney package! Learn more about these data
## sets at http://bit.ly/completejourney.

library(scales)

## 
## Attaching package: 'scales'
## 
## The following object is masked from 'package:purrr':
## 
##     discard
## 
## The following object is masked from 'package:readr':
## 
##     col_factor

transactions <- get_transactions()
#products <- products
#demographics <- demographics

vitamin <- transactions %>%
  inner_join(products, by = 'product_id') %>%
  filter(product_category == "VITAMINS") %>%  
  inner_join(demographics, by = "household_id") %>%
  group_by(income) %>%
  summarize(total_vitamin_purchased = sum(quantity, na.rm = TRUE), .groups = "drop") %>%
  arrange(income)

# Create a bar chart of Vitamins Purchased to Income level
ggplot(data = vitamin,  aes(x = factor(income, levels = unique(income)), y = total_vitamin_purchased, fill = income)) + geom_col() +
  labs(
    title = "Vitamin Purchases by Income Level",
    subtitle = "Total quantity of vitamins purchased across different income levels",
    x = "Income Level",
    y = "Total Quantity of Vitamins Purchased"
  ) +
  theme_minimal() 

brand_sales <- transactions %>%
  inner_join(products, by = "product_id") %>%
  group_by(brand) %>%
  summarise(total_sales = sum(sales_value, na.rm = TRUE), .groups = "drop") %>%
  arrange(desc(total_sales))

brand_sales <- brand_sales %>%
  mutate(percentage = total_sales / sum(total_sales) * 100)

#National Brands vs. Private Labels
ggplot(brand_sales, aes(x = "", y = percentage, fill = brand)) +
  geom_bar(stat = "identity", width = 1) +
  coord_polar(theta = "y", start = 0) +
  labs(
    title = "National Brands vs. Private Labels",
    subtitle = "Percentage share of total sales",
    y = NULL, 
    x = NULL
  ) +
  scale_y_continuous(labels = scales::percent_format(scale = 1)) +  # Convert to percentage labels
  theme_minimal()

age_product_sales <- transactions %>%
  inner_join(products, by = "product_id") %>%
  inner_join(demographics, by = "household_id") %>%
  group_by(age, product_category) %>% 
  summarise(total_sales = sum(sales_value, na.rm = TRUE), .groups = "drop") %>%
  arrange(age, desc(total_sales)) %>%  
  group_by(age) %>%
  slice_head(n = 5)

#Most Purchased Product Categories per Age Group
ggplot(age_product_sales, aes(x = total_sales, y = product_category, fill = age)) +
  geom_col() +
  facet_wrap(~age, scales = "free_y", ncol = 2) +
  labs(
    title = "Top 5 Most Purchased Product Categories per Age Group",
    subtitle = "Comparing product preferences across different age demographics",
    x = "Total Sales ($)",
    y = "Product Category"
  ) +
  theme_minimal()